SUSTAIN: a model of human category learning
AAAI '98/IAAI '98 Proceedings of the fifteenth national/tenth conference on Artificial intelligence/Innovative applications of artificial intelligence
Understanding intelligence
Information Theoretic Implications of Embodiment for Neural Network Learning
ICANN '97 Proceedings of the 7th International Conference on Artificial Neural Networks
Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Embodying cognitive abilities: categorization
IWANN'07 Proceedings of the 9th international work conference on Artificial neural networks
Development via information self-structuring of sensorimotor experience and interaction
50 years of artificial intelligence
SAB'06 Proceedings of the 9th international conference on From Animals to Animats: simulation of Adaptive Behavior
Hi-index | 0.00 |
The problem of category learning has been traditionally investigated by employing disembodied categorization models. One of the basic tenets of embodied cognitive science states that categorization can be interpreted as a process of sensory-motor coordination, in which an embodied agent, while interacting with its environment, can structure its own input space for the purpose of learning about categories. Many researchers, including John Dewey and Jean Piaget, have argued that sensory-motor coordination is crucial for perception and for development. In this paper we give a quantitative account of why sensory-motor coordination is important for perception and category learning.